Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix dynamic axes for ONNX models #1187

Merged
merged 3 commits into from
Jun 30, 2020
Merged

Fix dynamic axes for ONNX models #1187

merged 3 commits into from
Jun 30, 2020

Conversation

RobertLucian
Copy link
Member

@RobertLucian RobertLucian commented Jun 30, 2020

Fixes #1186.

It appears that setting the input shape to a generic string should signify to the user that the shape is dynamic and can be of any size. Currently, the Cortex ONNX client only checks if "dynamic_axes" is a substring of the shape dimension's value (if it's a string). As it appears to me, that's only a convention and the string can be set to anything.


checklist:

  • run make test and make lint
  • test manually (i.e. build/push all images, restart operator, and re-deploy APIs)

@RobertLucian RobertLucian added bug Something isn't working v0.18 labels Jun 30, 2020
@RobertLucian RobertLucian requested a review from deliahu June 30, 2020 00:16
Copy link
Member

@deliahu deliahu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks for catching and fixing this!

@RobertLucian RobertLucian merged commit 53c0b37 into master Jun 30, 2020
@RobertLucian RobertLucian deleted the fix/onnx-dynamic-axes branch June 30, 2020 05:17
vishalbollu pushed a commit that referenced this pull request Jun 30, 2020
@deliahu deliahu added this to the v0.18 milestone Nov 26, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

Successfully merging this pull request may close these issues.

"Failed to convert to numpy array for model '_cortex_default'" when making a prediction on an ONNX model
2 participants